{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:42:09Z","timestamp":1774456929401,"version":"3.50.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2003"],"award-info":[{"award-number":["U22A2003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20277"],"award-info":[{"award-number":["U23A20277"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271288"],"award-info":[{"award-number":["62271288"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Mobility Programme of Sino-German Cooperation and Exchange NSFC","award":["M-0626"],"award-info":[{"award-number":["M-0626"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3522298","type":"journal-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:26:48Z","timestamp":1735154808000},"page":"2199-2211","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Head Encoding for Extreme Label Classification"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7136-0482","authenticated-orcid":false,"given":"Daojun","family":"Liang","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5081-7287","authenticated-orcid":false,"given":"Haixia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9398-9238","authenticated-orcid":false,"given":"Dongfeng","family":"Yuan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Communication and Sensing-Computing Integration, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minggao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"17","article-title":"Quick training of probabilistic neural nets by importance sampling","volume-title":"Proc. Int. Workshop Artif. Intell. Statist.","author":"Bengio"},{"key":"ref2","first-page":"246","article-title":"Hierarchical probabilistic neural network language model","volume-title":"Proc. 10th Int. Workshop Artif. Intell. Statist.","author":"Morin"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.912312"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1186"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10362"},{"key":"ref7","first-page":"3069","article-title":"PD-sparse: A primal and dual sparse approach to extreme multiclass and multilabel classification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yen"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018741"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939756"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080834"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623651"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185998"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05888-2"},{"key":"ref14","first-page":"6358","article-title":"A no-regret generalization of hierarchical softmax to extreme multi-label classification","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Wydmuch"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3542629"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3097987"},{"key":"ref17","first-page":"5820","article-title":"AttentionXML: Label tree-based attention-aware deep model for high-performance extreme multi-label text classification","volume-title":"Proc. 33rd Neural Inf. Process. Syst.","author":"You"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403368"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16974"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12337"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00166"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119334"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3136592"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/sapm192761164"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289464"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90014-2"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2835403"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-436"},{"key":"ref33","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref37","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma"},{"issue":"1","key":"ref38","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref39","first-page":"876","article-title":"Averaging weights leads to wider optima and better generalization","volume-title":"Proc. 34th Conf. Uncertainty Artif. Intell.","author":"Izmailov"},{"key":"ref40","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv: 1810.04805"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref42","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2935143"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00566"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.87"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICB2018.2018.00033"},{"key":"ref52","first-page":"1","article-title":"Labeled faces in the wild: A database for studying face recognition in unconstrained environments","volume-title":"Proc. Workshop Faces in\u2019Real-Life\u2019Images: Detection, Alignment, Recognit.","author":"Huang"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.250"},{"key":"ref54","article-title":"Cross-age LFW: A database for studying cross-age face recognition in unconstrained environments","author":"Zheng","year":"2017","journal-title":"arXiv: 1708.08197"},{"issue":"7","key":"ref55","first-page":"5","article-title":"Cross-pose LFW: A database for studying cross-pose face recognition in unconstrained environments","volume":"5","author":"Zheng","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477558"},{"key":"ref57","first-page":"479","article-title":"OPUS-MT \u2014 Building open translation services for the World","volume-title":"Proc. 22nd Annu. Conf. Eur. Assoc. Mach. Trans.","author":"Tiedemann"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3210"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_15"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3174892"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.39"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.03.009"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5256-5"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10816186.pdf?arnumber=10816186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T06:01:11Z","timestamp":1738821671000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10816186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":64,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3522298","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}